Search

Neste trabalho, apresentam-se algumas técnicas e tecnologias da web semântica para demonstrar a sua aplicação no campo da medicina, mais precisamente em sistemas para a identificação de informação médica em relatórios clínicos. Descrevemos a utilização da web semântica no desenvolvimento desses sistemas. O trabalho desenvolvido define os processos que, pela avaliação dos históricos clínicos de pacientes, identifiquem os termos de importância semântica para a recuperação da informação clínica nestes relatórios.

We present the work done as a contribution to use an enriched ontology as the support for Semantic Interoperability among technicians and systems in healthcare providing environments. Clinical practice ontologies are the next generation workhorse for automatic reasoning using Semantic Web techniques and tools in the healthcare sub-domain. Acquisition from semi-structured data that renders a full picture of the general clinical practice is crucial for solid enrichment of an Ontology that is designed to embrace the generality of information located in EHR systems. These systems communicate syntactically using HL7 standardized messaging but must evolve to semantic interoperability based in a well formed standardized semantic like CPR. Automated acquisition is absolutely a must given the enormous amounts of information available in the mentioned sources. Recent efforts directed to solve the overwhelming complexity of HL2 CDA archetype, like the greenCDA template proposal, along with computability gained with OWL DL ontologies reasoning is leading to the possibility of development of foundations for strong Clinical Decision Support tools and Computable Semantic Interoperability representations in the Semantic Web. As an intermediate step to acquisition from standardized messaging we present the ontology population/enrichment taken from the widespread framework for communication that is the SOAP (Subjective, Objective, Assessment, Plan) clinical encounters documenting system.

In this paper we propose a Cooperative Question Answering System that takes as input natural language queries and is able to return a cooperative answer based on semantic web resources, more specifically DBpedia represented in OWL/RDF as knowledge base and WordNet to build similar questions. Our system resorts to ontologies not only for reasoning but also to find answers and is independent of prior knowledge of the semantic resources by the user. The natural language question is translated into its semantic representation and then answered by consulting the semantics sources of information. The system is able to clarify the problems of ambiguity and helps finding the path to the correct answer. If there are multiple answers to the question posed (or to the similar questions for which DBpedia contains answers), they will be grouped according to their semantic meaning, providing a more cooperative answer to the user.

In this paper we propose a Cooperative Question Answering System that takes as input queries expressed in natural language and is able to return a cooperative answer obtained from resources in the Semantic Web, more specifically DBpedia represented in OWL/RDF as knowledge base and WordNet to build similar questions. Our system resorts to ontologies not only for reasoning but also to find answers and is independent of prior knowledge of the semantic resources by the user. The natural language question is translated into its semantic representation and then answered by consulting the semantics information sources. If there are multiple answers to the question posed (or to the similar questions for which DBpedia contains answers), they will be grouped according to their semantic meaning, providing a more cooperative and clean answer to the user.

Neste artigo apresentamos a metodologia seguida para a construc ̧a ̃o de um sistema de pergunta- resposta sobre uma base de documentos em Portuguˆes. Descrevemos o sistema que tem dois mo ́dulos distintos: ana ́lise pr ́evia dos documentos (extracc ̧a ̃o de informac ̧a ̃o) e processamento das perguntas (recuperac ̧a ̃o de informac ̧a ̃o). O nosso sistema procura fazer um processamento, do corpus e da perguntas, suportado em teorias da lingu ́ıstica computacional: ana ́lise sinta ́ctica (grama ́tica de restric ̧o ̃es), seguida da ana ́lise semaˆntica usando a teoria da representac ̧a ̃o do discurso e finalmente a interpretac ̧a ̃o semaˆntica/pragma ́tica usando ontologia e inferˆencia lo ́gica. Apresentamos resultados da avaliac ̧a ̃o do seu desempenho que foi feita sobre dois conjuntos de documentos: textos de dois anos de jornais dia ́rios, o Pu ́blico e a Folha de Sa ̃o Paulo (1994-1995); e um conjunto de documentos jur ́ıdicos: deciso ̃es do supremo Tribunal, tribunal da Relac ̧a ̃o e pareceres da Procuradoria Geral da Repu ́blica (cerca de 100.000 documentos).